检索结果-内蒙古大学图书馆

11th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2024

作者： Anggara, Muchamad Galih Hindasyah, Ahmad Amda, Julfa Muhammad Waskita, A.A. Graduate Program of Informatics Engineering Universitas Pamulang Pamulang Indonesia Research Center for Computing National Research and Innovation Agency Cibinong Indonesia Research Center for Data and Information Sciences National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798331542313

Accurate image classification of microscopic pathogenic fungi is a challenge in the field of mycology. This study proposes a Swin Transformer-based approach to automate the identification process. The Swin Transformer model, known for its ability to capture complex spatial interactions, is adapted from ImageNet’s pre-trained model. The adaptation process is focused on fine-tuning the final classification layer to match the 5 classes of fungi present in the dataset. This classification layer is replaced by a new fully-connected layer that has the number of output according to the number of fungal classes. The weights on these layers are randomly initialized and trained in conjunction with several final convolutional layers. In addition, regularization techniques such as dropouts are applied to prevent overfitting. Adaptation using 5-fold cross-validation was carried out to find the best fold with hyperparameters including AdamW optimizer with a learning rate of 10−3, StepLR scheduler, batch size of 128 images, and a total of 9 epochs / iterations. After that, fine-tuning is carried out on the best fold with hyperparameters including AdamW optimizer with a learning rate of 10−5, StepLR scheduler, batch size of 32 images, and a total of 100 epochs / iterations. The final result showed excellent performance, with accuracy, precision, recall and an average F1-score of 95%. These results show the potential of the Swin Transformer in becoming an effective tool for mycologists. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

InfoGain Wavelets: Furthering the Design of Diffusion Wavelets for Graph-Structured Data

arXiv

引用

arXiv 2025年

作者： Johnson, David R. Krishnaswamy, Smita Perlmutter, Michael Program in Computing Boise State University BoiseID United States Department of Computer Science Department of Genetics Yale University New HavenCT United States Department of Mathematics Program in Computing Boise State University BoiseID United States

Diffusion wavelets extract information from graph signals at different scales of resolution by utilizing graph diffusion operators raised to various powers, known as diffusion scales. Traditionally, the diffusion scales are chosen to be dyadic integers, 2j. Here, we propose a novel, unsupervised method for selecting the diffusion scales based on ideas from information theory. We then show that our method can be incorporated into wavelet-based GNNs via graph classification experiments. Copyright © 2025, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Landing Guidance Through Tracking and Orientation Estimation

Vision-Based Landing Guidance Through Tracking and Orientati...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： João P. K. Ferreira João P. Pinto Júlia Moura Yi Li Cristiano L. Castro Plamen Angelov Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais School of Computing and Communications Lancaster University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Fixed-wing aerial vehicles are equipped with functional-ities such as ILS (instrument landing system), PAR (precision approach radar) and, DGPS (differential global positioning system), enabling fully automated landings. How-ever, these systems impose significant costs on airport op-erations due to high installation and maintenance requirements. Moreover, since these navigation parameters come from ground or satellite signals, they are vulnerable to in-terference. A more cost-effective and independent alternative for guiding landing is a vision-based system that de-tects the runway and aligns the aircraft, reducing the pi-lot's cognitive load. This paper proposes a novel frame-work that addresses three key challenges in developing au-tonomous vision-based landing systems. Firstly, to over-come the lack of aerial front-view video data, we created high-quality videos simulating landing approaches through the generator code available in the LARD (landing approach runway detection dataset) repository. Secondly, in contrast to former studies focusing on object detection for finding the runway, we chose the state-of-the-art model Lo-RAT to track runways within bounding boxes in each video frame. Thirdly, to align the aircraft with the designated landing runway, we extract runway keypoints from the re-sulting LoRAT frames and estimate the camera relative pose via the Perspective-n-Point algorithm. Our experimental re-sults over a dataset of generated videos and original images from the LARD dataset consistently demonstrate the proposed framework's highly accurate tracking and alignment capabilities. Our approach source code and the Lo-RAT model pre-trained with LARD videos are available at https://***/jpklock2/vision-based-landing-guidance

关键词： Visualization Codes Accuracy Atmospheric modeling Pose estimation Video sequences Radar tracking Generators Aircraft navigation Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Watermarking System Through Approximate Discrete Haar Wavelet Transform

Energy-Efficient Watermarking System Through Approximate Dis...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Thiago Rutz Morgana Da Rosa Rodrigo Lopes Eduardo Da Costa Rafael Soares Sergio Bampi Graduate Program on Computing - Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing - Catholic University of Pelotas (UCPel) Pelotas Brazil Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

This work introduces a low-energy-driven watermarking system that employs the approximate discrete Haar Wavelet transform (AxDHWT) to insert watermark images into host images. Our contribution involves developing an energy-efficient AxDHWT watermarking system in VLSI hardware. Additionally, we present a model implemented in MATLAB, incorporating probability theory for accuracy estimation, along with extensive testing conducted under diverse attack scenarios. Logic synthesis (LS) results show that the AxDHWT watermarking system demonstrates low power and reduces area cost, featuring ten fewer arithmetic circuits than the current state-of-the-art. Remarkably, our AxDHWT-based architecture showcases reductions of $1.33\times$ in area and $2.88\times$ in energy consumption compared to the state-of-the-art system.

关键词： Salt Transform coding Watermarking Transforms Very large scale integration Speckle Energy efficiency Discrete wavelet transforms Testing Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Identifying the computing Education Needs of Liberal Arts and Sciences Students (Discussion Paper) 23

Identifying the Computing Education Needs of Liberal Arts an...

引用

Proceedings of the 23rd Koli Calling International Conference on computing Education Research

作者： Mark Guzdial August Evrard Computer Science & Engineering University of Michigan USA Program in Computing for the Arts and Sciences University of Michigan USA

ISBN: (纸本)9798400716539

As a field, computing’s deepest roots lie in liberal arts domains such as philosophy and linguistics. As new technologies rapidly expanded the field, the computer science curricula emerged. The current undergraduate areas of study, including computer science and software engineering, focus on preparing students for careers in the computing industry or academia. The “born digital” students of a modern liberal arts institution need a different, less technology-heavy, form of computing education to support their careers as future scientists, artists, or humanists. At our large, research-focused, US university, the College of Literature, Science, and the Arts (LSA) charged a task force with defining the computing education needs for their students, chaired by the authors. We describe our process, findings and outcomes here with the aim of offering a reference template to faculty at universities that have experienced a similar growth to prominence of computer science in the undergraduate curriculum. The task force identified emergent themes of discovery, expression, and justice that we using to establish a new program, the program for computing in the Arts and Sciences (PCAS). Our themes and process may help other liberal arts and sciences programs organize the computing education needs in support of all their undergraduate students.

关键词： CS for All computational literacy computational science computational thinking critical computing liberal arts and sciences

来源：评论

学校读者我要写书评

暂无评论

Families of Multidimensional Periodic Arrays with Optimal Low Cross-Correlation 1st

Families of Multidimensional Periodic Arrays with Optimal Lo...

引用

1st International Symposium on Intelligent computing and Networking, ISICN 2024

作者： Bolaños, César Bollman, Dorothy Doctoral Program in Computing and Information Sciences and Engineering University of Puerto Rico at Mayagüez Mayagüez00680 Puerto Rico Department of Mathematical Sciences University of Puerto Rico at Mayagüez Mayagüez00680 Puerto Rico

ISBN: (纸本)9783031674464

We construct new families of multidimensional periodic arrays that can be used for digital watermarking videos and images. Each member of each family is composed of columns of cyclic shifts of a Sidelnikov sequence in which the shifts are given by a multidimensional m1×m2×…×mn "grid" that is determined by applying a logarithmic quadratic map to the elements of a direct product Zm1×Zm2×…×Zmn. These arrays have peak auto-correlation on the order of p2l and non-peak auto- and cross-correlation on the order of pl, where l≥2 and m1m2…mn=pl-1, thereby improving the peak auto-correlation to nonpeak auto- and cross-correlations of other known constructions. Additionally, we show that the low cross-correlation values are optimal with respect to the Welch bound. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Scaffolding Process-Aware Information Systems with the AKIP Platform 1

引用

18th International Conference on Web Information Systems and Technologies, WEBIST 2022

作者： Telemaco Neto, Ulisses Oliveira, Toacy Pillat, Raquel Alencar, Paulo Cowan, Don Melo, Glaucia David R. Cheriton School of Computer Science University of Waterloo Waterloo Canada System Engineering and Computing Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (数字)9783031430886

ISBN: (纸本)9783031430879

Business Process Automation (BPA) refers to the automation of business processes through technology, with the goal of improving efficiency, reducing errors, and increasing productivity by eliminating manual and repetitive tasks. Over the past few years, the number of BPA platforms has increased, including both open-source and proprietary solutions. However, some challenges and limitations still exist related to the adoption of these solutions, such as vendor lock-in, limited UI/UX, limited integration, outdated technology stack, and lack of support for non-process features. To address these issues, this paper presents the AKIP platform, an open-source framework for developing process-aware information systems (PAISs) using code generation techniques. AKIP generates functional process-aware web applications from BPMN business process models, making it the only known software tool capable of generating fully functional process-aware web applications. To evaluate the effectiveness of the AKIP platform, a case study was conducted in the industry and six business processes automated into a process-oriented web application were analyzed in this paper. The study showed that the AKIP platform was able to generate a functional web application while supporting the automation of business processes with different model sizes and complexities. Furthermore, this study showed that even a team of professionals with little experience was able to produce such results by using the AKIP platform. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Averaged Model of DCM-Operated Boost Converter Fed by PV Source 4

Comprehensive Averaged Model of DCM-Operated Boost Converter...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Fairouz, Fatima A Elgendy, Mohammed A Muhammed, Musbahu Newcastle University School of Engineering Newcastle Upon Tyne United Kingdom Renewable Energy Program Kuwait Institute for Scientific Research Industrial Shuwaikh Kuwait Teesside University School of Computing Engineering & Digital Technologies Middlesbrough United Kingdom

ISBN: (纸本)9798350306262

The average model of DC-DC converters is commonly used to analyze the control stability and dynamics of switched-mode converters. Although the average model of the boost converter (BC) in the continuous conduction mode (CCM) and the discontinuous conduction modes (DCM) is well-covered in the literature, the modelling and control of the DCM-operated BC with the maximum power point tracking (MPPT) has not been paid much attention. In this paper, a comprehensive state-space averaged model of DCM-operated BC fed by photovoltaic (PV) source is derived. Higher-order, lower-order, reduced-order, and full-order models are considered. MATLAB simulation is used to verify the derived models. The converter dynamics were analyzed based on the bode-plot and the step-response for each model. Results show that the lower-full-order model is considered the most suitable choice for modelling the DCM-operated boost converter. © 2024 IEEE.

关键词： Boost converter

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Healthprompt for Zero-shot Clinical Text Classification 11

Evaluation of Healthprompt for Zero-shot Clinical Text Class...

引用

11th IEEE International Conference on Healthcare Informatics, ICHI 2023

作者： Sivarajkumar, Sonish Wang, Yanshan University of Pittsburgh Intelligent Systems Program School of Computing and Information Pittsburgh United States University of Pittsburgh School of Health and Rehabilitation Sciences Department of Health Information Management Pittsburgh United States

ISBN: (纸本)9798350302639

This paper presents an evaluation of the Healthprompt, a prompt-based zero-shot clinical text classification framework. The lack of publicly available datasets and the expensive data annotation in the clinical domain make traditional NLP models difficult to train. To overcome this issue, Healthprompt utilizes Pre-trained Language Models (PLMs) and prompt-based Zero-Shot Learning (ZSL) to perform clinical NLP tasks without additional training data. However, the original Healthprompt paper missed the error analysis and ablation study of the framework. This paper conducts an error analysis and an ablation study on Electronic Health Records(EHR) notes to understand the capabilities and limitations of the Healthprompt framework for clinical text classification. The results provide insight into the potential and limitations of prompt-based zeroshot learning for clinical NLP tasks and offer suggestions for improvements to the Healthprompt framework, and for the future development of prompt-based ZSL. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Acceptance Analysis of IWB Systems in Education using UTAUT2 Model: The Moderating Role of Perceived Technological Innovations

Acceptance Analysis of IWB Systems in Education using UTAUT2...

引用

2023 IEEE International Conference on Automatic Control and Intelligent Systems, I2CACIS 2023

作者： De Jesus, Noelyn Castro, Eltimar T. Buyan, Cory Antonio Batangas State University College of Informatics & Computing Sciences Batangas Philippines Technological Institute of the Philippines Graduate Program Department Manila Philippines Ballard Power Systems Business Technology Burnaby Canada

ISBN: (纸本)9798350321302

Interactive Whiteboard (IWB) Systems are increasingly being used to replace traditional whiteboards in educational activities, making them more efficient and interesting for both teachers and students. However, no studies have been conducted to investigate how age, educational level, and employment status can impact the adoption and usage of IWB systems in the educational setting. The study aims to analyze the acceptance and the influencing factors on faculty members' intention and usage behavior towards IWB systems in teaching, utilizing the Modified-Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model. 135 faculty members from various colleges and departments across Batangas State University ARASOF-Nasugbu Campus were surveyed and data was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) through SmartPLS software for hypotheses testing. The results of the study indicate that faculty members' behavioral intention to use interactive whiteboard systems in teaching is positively influenced by performance expectancy and social influence. Moreover, facilitating conditions and habit positively impact usage behavior. This study, therefore, concludes that there is significant roles of performance expectancy and social influence as well as the moderating effect of age on the behavioral intention to use interactive whiteboard (IWB) systems in education. Furthermore, the study confirms that effort expectancy, hedonic motivation, and status as moderating variables significantly influence faculty members' usage behavior when using IWB systems in teaching. © 2023 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：